Open AccessDistribution of scarce resources based on crowd density detection and queuing theory
Author(s) -
Tingxuan Zhang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1486/5/052034
Subject(s) - queueing theory , convolution (computer science) , set (abstract data type) , computer science , population , density estimation , estimation , mathematical optimization , statistics , engineering , mathematics , artificial intelligence , computer network , demography , systems engineering , estimator , sociology , artificial neural network , programming language
This paper makes a reasonable estimate of the number of charging stations to be set in each charging station by detecting the density of people near the charging station. Due to the shortcomings of traditional MCNNs that are currently commonly used for population density estimation, we added dilated convolution to the traditional MCNN and applied queuing theory to this problem. The population density estimation result of the MCNN incorporating the reduced convolution is used as the input of the aligned flow, so that the number of charging piles in each charging station is more reasonably set.